概率积分法预计参数选取的神经网络模型  

Artificial Neural Network Model for Predicting Parameters of Probability-Integral Method

作　　者：郭文兵[1] 邓喀中[2] 邹友峰[1] 

机构地区：[1]焦作工学院资源与材料工程系,河南焦作454000 [2]中国矿业大学环境与测绘学院,江苏徐州221008

出　　处：《中国矿业大学学报》2004年第3期322-326,共5页Journal of China University of Mining & Technology

基　　金：国家自然科学基金项目(50174051);河南省自然科学基金项目(0311053100);河南省优秀中青年骨干教师基金项目

摘　　要：在综合分析概率积分法参数与地质采矿条件之间关系的基础上,采用人工神经网络方法建立了概率积分法参数选取的模型.模型采用改进的BP优化算法,运用我国典型的地表移动观测站资料作为学习训练样本和测试样本,对网络模型的计算结果与实测值进行了对比分析.分析结果表明:用人工神经网络方法求算概率积分法参数结果更接近于实际.对提高开采沉陷预计精度具有积极意义.On the basis of analyaing the relationship between parameters of probability-integral method and geologic and mining conditions the model to calculate the parameters of probability-integral method was established by applying the theory of artificial neural network (ANN). A large amount from data of observation stations was used as learning and training samples to train and test the artificial neural network model by optimal arithmetic. The calculation results of the ANN model and the observed values were analyzed and compared with each other. The results show that it is more precise to predicting the parameters of probability-integral method by ANN technology and can make a contribution to enhance the precision of the predicted prarmeters for mining subsidence.

关 键 词：概率积分法 地质采矿 神经网络模型 地表移动参数 开采沉陷 

分 类 号：TD325.2[矿业工程—矿井建设] TP183[自动化与计算机技术—控制理论与控制工程]